Ticket API MCP Server
An MCP server exposing the internal Ticket API to MCP clients, built with FastMCP's OpenAPI integration.
README
Ticket API MCP Server
An MCP server exposing the internal Ticket API to MCP clients, built with FastMCP's OpenAPI integration.
Architecture & Authentication
The upstream API uses a two-hop auth model (static API Key + per-user short-lived JWT). This server bridges it to MCP clients by minting long-lived Personal Access Tokens (PATs) and transparently handling upstream JWT refresh.
sequenceDiagram
participant Client as MCP Client
participant Server as Ticket MCP Server
participant DB as SQLite (Encrypted)
participant Upstream as Upstream Ticket API
Note over Client, Server: 1. One-time Setup
Client->>Server: POST /register (username, password)
Server->>Upstream: Validate credentials
Server->>DB: Store hashed PAT & encrypted password
Server-->>Client: Returns never-expiring PAT (tkt_...)
Note over Client, Server: 2. Ongoing Tool Calls
Client->>Server: Tool Call (Bearer PAT)
Server->>DB: Verify PAT hash
alt Cached JWT expired/missing
Server->>DB: Decrypt password
Server->>Upstream: Re-login to get fresh JWT
end
Server->>Upstream: Forward Tool Call + Bearer JWT
Upstream-->>Server: Tool response
Server-->>Client: Tool response
Running Locally
pip install -e ".[dev]"
cp .env.example .env # Fill in keys
ticket-mcp-server
# MCP endpoint: http://localhost:8000/sse
# Register a PAT: POST http://localhost:8000/register {"username": "...", "password": "..."}
# Revoke a PAT: POST http://localhost:8000/revoke (Authorization: Bearer <PAT>)
# Health check: GET http://localhost:8000/health (unauthenticated)
Connect with any MCP client using the standard SSE transport at http://localhost:8000/sse with Authorization: Bearer <your-tkt_-token>.
Running with Docker
docker build -t ticket-mcp-server .
docker run -p 8000:8000 \
-v ticket-mcp-data:/app/data \
-e TICKET_MCP_UPSTREAM_API_KEY=<your-service-key> \
-e TICKET_MCP_CREDENTIAL_ENCRYPTION_KEY=<your-fernet-key> \
ticket-mcp-server
(Note: The -v volume mount is required to persist PATs across container restarts.)
Configuration
Set via environment variables (prefix TICKET_MCP_):
| Variable | Required | Default | Description |
|---|---|---|---|
TICKET_MCP_UPSTREAM_API_KEY |
yes | — | Service-level X-API-Key |
TICKET_MCP_CREDENTIAL_ENCRYPTION_KEY |
yes | — | Fernet key for credentials |
TICKET_MCP_UPSTREAM_BASE_URL |
no | https://hffyacypdj.ap-south-1.awsapprunner.com |
Upstream API base URL |
TICKET_MCP_CREDENTIAL_DB_PATH |
no | ./data/credentials.db |
SQLite PAT store |
TICKET_MCP_HOST / PORT |
no | 0.0.0.0 / 8000 |
Bind host/port |
Generate an encryption key:
python -c "from cryptography.fernet import Fernet; print(Fernet.generate_key().decode())"
Tests
pip install -e ".[dev]"
pytest -v
(Tests use a mock upstream API to safely exercise the full PAT lifecycle.)
Copyright©️ Codebasics Inc. All rights reserved.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.